DIOR: Dataset for Indoor-Outdoor Reidentification Long Range 3D/2D Skeleton Gait Collection Pipeline, Semi-Automated Gait Keypoint Labeling and Baseline Evaluation Methods

Abstract

DIOR presents a long-range indoor-outdoor gait data collection and annotation framework for person re-identification. The work combines 3D computer vision and learning-based components to generate 3D/2D skeleton gait labels from indoor motion-capture settings and outdoor long-range camera views, supporting evaluation of recognition methods beyond face-only biometrics.

Publication
IEEE International Joint Conference on Biometrics (IJCB), 2024